fix: alfworld rollout prompt

Author: realtmxi

openmanus_rl/environments/env_manager.py

@@ -107,9 +107,11 @@ def build_text_obs(self, text_obs: List[str], admissible_actions: List[List[str]
             reformatted_admissible_actions = "\n ".join(f"'{s}'" for s in admissible_actions[i] if s != 'help')
 
             if init or self.config.env.history_length <= 0:
+                # Include task_description to satisfy ALFWORLD_TEMPLATE_NO_HIS placeholders.
                 obs = ALFWORLD_TEMPLATE_NO_HIS.format(
+                    task_description=self.tasks[i],
                     current_observation=text_obs[i],
-                    admissible_actions=reformatted_admissible_actions
+                    admissible_actions=reformatted_admissible_actions,
                 )
             else:
                 obs = ALFWORLD_TEMPLATE.format(

openmanus_rl/environments/prompts/alfworld.py

@@ -5,7 +5,7 @@
 # Your admissible actions of the current situation are: [{admissible_actions}].
 
 # Now it's your turn to take an action.
-# You should first reason step-by-step about the current situation. This reasoning process MUST be enclosed within <think> </think> tags. 
+# You should first reason step-by-step about the current situation. This reasoning process MUST be enclosed within <plan> </plan> tags. 
 # Once you've finished your reasoning, you should choose an admissible action for current step and present it within <action> </action> tags.
 # """
 
@@ -54,7 +54,7 @@
 - Am I making progress toward the task goal?
 </reflection>
 
-After that, you should plan the next step based on memory and reflection, then MUST summarize within <think> </think> tags like this:
+After that, you should plan the next step based on memory and reflection, then MUST summarize within <plan> </plan> tags like this:
 
 <plan>
 [Plan the next step based on memory and reflection]